Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmbert_tiny-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
65819cd
·
1 Parent(s): 58c1759

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697793703.46dc0c540dd0.5704.4 +3 -0
  5. test.tsv +0 -0
  6. training.log +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec7614f565f822cff91f0521a85492ac634f284b7cb9fe484884379da57343e
3
+ size 19045986
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 09:22:08 0.0000 0.7355 0.1224 0.0000 0.0000 0.0000 0.0000
3
+ 2 09:22:34 0.0000 0.1957 0.1019 0.4656 0.3713 0.4131 0.2675
4
+ 3 09:22:59 0.0000 0.1705 0.0931 0.4648 0.5021 0.4828 0.3278
5
+ 4 09:23:24 0.0000 0.1558 0.0940 0.5256 0.5190 0.5223 0.3650
6
+ 5 09:23:49 0.0000 0.1474 0.0924 0.5055 0.5865 0.5430 0.3850
7
+ 6 09:24:13 0.0000 0.1391 0.0939 0.5597 0.5738 0.5667 0.4096
8
+ 7 09:24:38 0.0000 0.1339 0.0905 0.5437 0.5781 0.5603 0.4029
9
+ 8 09:25:03 0.0000 0.1286 0.0943 0.5542 0.5823 0.5679 0.4107
10
+ 9 09:25:28 0.0000 0.1271 0.0943 0.5870 0.5696 0.5782 0.4219
11
+ 10 09:25:53 0.0000 0.1244 0.0944 0.5763 0.5738 0.5751 0.4185
runs/events.out.tfevents.1697793703.46dc0c540dd0.5704.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63253d602cf2d9f93fc9f5ecf08a9af058dd1e627fc7409368ce4b0958596737
3
+ size 864636
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-20 09:21:43,922 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-20 09:21:43,922 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-20 09:21:43,922 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-20 09:21:43,922 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
52
+ - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
53
+ 2023-10-20 09:21:43,922 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-20 09:21:43,922 Train: 6183 sentences
55
+ 2023-10-20 09:21:43,922 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-20 09:21:43,922 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-20 09:21:43,922 Training Params:
58
+ 2023-10-20 09:21:43,922 - learning_rate: "3e-05"
59
+ 2023-10-20 09:21:43,922 - mini_batch_size: "4"
60
+ 2023-10-20 09:21:43,922 - max_epochs: "10"
61
+ 2023-10-20 09:21:43,923 - shuffle: "True"
62
+ 2023-10-20 09:21:43,923 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-20 09:21:43,923 Plugins:
64
+ 2023-10-20 09:21:43,923 - TensorboardLogger
65
+ 2023-10-20 09:21:43,923 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-20 09:21:43,923 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-20 09:21:43,923 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-20 09:21:43,923 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-20 09:21:43,923 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-20 09:21:43,923 Computation:
71
+ 2023-10-20 09:21:43,923 - compute on device: cuda:0
72
+ 2023-10-20 09:21:43,923 - embedding storage: none
73
+ 2023-10-20 09:21:43,923 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-20 09:21:43,923 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-20 09:21:43,923 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-20 09:21:43,923 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-20 09:21:43,923 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-20 09:21:46,109 epoch 1 - iter 154/1546 - loss 2.48451865 - time (sec): 2.19 - samples/sec: 5594.24 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-20 09:21:48,505 epoch 1 - iter 308/1546 - loss 2.20980853 - time (sec): 4.58 - samples/sec: 5428.83 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-20 09:21:50,962 epoch 1 - iter 462/1546 - loss 1.82421682 - time (sec): 7.04 - samples/sec: 5172.98 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-20 09:21:53,386 epoch 1 - iter 616/1546 - loss 1.48474101 - time (sec): 9.46 - samples/sec: 5109.95 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-20 09:21:55,723 epoch 1 - iter 770/1546 - loss 1.25106887 - time (sec): 11.80 - samples/sec: 5093.22 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-20 09:21:58,079 epoch 1 - iter 924/1546 - loss 1.08823913 - time (sec): 14.16 - samples/sec: 5114.37 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-20 09:22:00,454 epoch 1 - iter 1078/1546 - loss 0.95790324 - time (sec): 16.53 - samples/sec: 5192.58 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-20 09:22:02,788 epoch 1 - iter 1232/1546 - loss 0.87119296 - time (sec): 18.86 - samples/sec: 5187.38 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-20 09:22:05,208 epoch 1 - iter 1386/1546 - loss 0.79808934 - time (sec): 21.28 - samples/sec: 5193.97 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-20 09:22:07,613 epoch 1 - iter 1540/1546 - loss 0.73692287 - time (sec): 23.69 - samples/sec: 5231.99 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-20 09:22:07,698 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-20 09:22:07,698 EPOCH 1 done: loss 0.7355 - lr: 0.000030
90
+ 2023-10-20 09:22:08,681 DEV : loss 0.1223587766289711 - f1-score (micro avg) 0.0
91
+ 2023-10-20 09:22:08,694 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-20 09:22:11,055 epoch 2 - iter 154/1546 - loss 0.23461614 - time (sec): 2.36 - samples/sec: 5266.33 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-20 09:22:13,484 epoch 2 - iter 308/1546 - loss 0.22531020 - time (sec): 4.79 - samples/sec: 5142.15 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-20 09:22:15,947 epoch 2 - iter 462/1546 - loss 0.20946648 - time (sec): 7.25 - samples/sec: 5161.02 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-20 09:22:18,269 epoch 2 - iter 616/1546 - loss 0.20751780 - time (sec): 9.57 - samples/sec: 5222.26 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-20 09:22:20,610 epoch 2 - iter 770/1546 - loss 0.19961546 - time (sec): 11.91 - samples/sec: 5227.20 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-20 09:22:22,995 epoch 2 - iter 924/1546 - loss 0.19714712 - time (sec): 14.30 - samples/sec: 5174.61 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-20 09:22:25,327 epoch 2 - iter 1078/1546 - loss 0.19697459 - time (sec): 16.63 - samples/sec: 5174.54 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-20 09:22:27,676 epoch 2 - iter 1232/1546 - loss 0.19565618 - time (sec): 18.98 - samples/sec: 5183.60 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-20 09:22:30,107 epoch 2 - iter 1386/1546 - loss 0.19351339 - time (sec): 21.41 - samples/sec: 5184.12 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-20 09:22:32,820 epoch 2 - iter 1540/1546 - loss 0.19609873 - time (sec): 24.13 - samples/sec: 5131.95 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-20 09:22:32,914 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-20 09:22:32,915 EPOCH 2 done: loss 0.1957 - lr: 0.000027
104
+ 2023-10-20 09:22:34,291 DEV : loss 0.10185166448354721 - f1-score (micro avg) 0.4131
105
+ 2023-10-20 09:22:34,302 saving best model
106
+ 2023-10-20 09:22:34,336 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-20 09:22:36,711 epoch 3 - iter 154/1546 - loss 0.17535207 - time (sec): 2.37 - samples/sec: 5156.66 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-20 09:22:39,106 epoch 3 - iter 308/1546 - loss 0.18337472 - time (sec): 4.77 - samples/sec: 5116.39 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-20 09:22:41,362 epoch 3 - iter 462/1546 - loss 0.17696955 - time (sec): 7.03 - samples/sec: 5168.68 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-20 09:22:43,760 epoch 3 - iter 616/1546 - loss 0.17228177 - time (sec): 9.42 - samples/sec: 5189.50 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-20 09:22:46,138 epoch 3 - iter 770/1546 - loss 0.16767539 - time (sec): 11.80 - samples/sec: 5203.89 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-20 09:22:48,495 epoch 3 - iter 924/1546 - loss 0.16675286 - time (sec): 14.16 - samples/sec: 5206.07 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-20 09:22:50,831 epoch 3 - iter 1078/1546 - loss 0.16667390 - time (sec): 16.49 - samples/sec: 5214.07 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-20 09:22:53,279 epoch 3 - iter 1232/1546 - loss 0.16837749 - time (sec): 18.94 - samples/sec: 5220.26 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-20 09:22:55,532 epoch 3 - iter 1386/1546 - loss 0.16869676 - time (sec): 21.20 - samples/sec: 5269.06 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-20 09:22:57,935 epoch 3 - iter 1540/1546 - loss 0.17071969 - time (sec): 23.60 - samples/sec: 5249.18 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-20 09:22:58,025 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-20 09:22:58,025 EPOCH 3 done: loss 0.1705 - lr: 0.000023
119
+ 2023-10-20 09:22:59,119 DEV : loss 0.09305855631828308 - f1-score (micro avg) 0.4828
120
+ 2023-10-20 09:22:59,130 saving best model
121
+ 2023-10-20 09:22:59,169 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-20 09:23:01,533 epoch 4 - iter 154/1546 - loss 0.18946194 - time (sec): 2.36 - samples/sec: 5331.47 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-20 09:23:03,986 epoch 4 - iter 308/1546 - loss 0.15783265 - time (sec): 4.82 - samples/sec: 5292.11 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-20 09:23:06,399 epoch 4 - iter 462/1546 - loss 0.15915683 - time (sec): 7.23 - samples/sec: 5311.71 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-20 09:23:08,748 epoch 4 - iter 616/1546 - loss 0.15503094 - time (sec): 9.58 - samples/sec: 5278.97 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-20 09:23:11,091 epoch 4 - iter 770/1546 - loss 0.15482979 - time (sec): 11.92 - samples/sec: 5251.65 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-20 09:23:13,444 epoch 4 - iter 924/1546 - loss 0.15581642 - time (sec): 14.27 - samples/sec: 5225.36 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-20 09:23:15,828 epoch 4 - iter 1078/1546 - loss 0.15477132 - time (sec): 16.66 - samples/sec: 5195.01 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-20 09:23:18,190 epoch 4 - iter 1232/1546 - loss 0.15524974 - time (sec): 19.02 - samples/sec: 5213.98 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-20 09:23:20,514 epoch 4 - iter 1386/1546 - loss 0.15589324 - time (sec): 21.34 - samples/sec: 5239.09 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-20 09:23:22,914 epoch 4 - iter 1540/1546 - loss 0.15641620 - time (sec): 23.74 - samples/sec: 5201.94 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-20 09:23:23,014 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-20 09:23:23,014 EPOCH 4 done: loss 0.1558 - lr: 0.000020
134
+ 2023-10-20 09:23:24,084 DEV : loss 0.09403558075428009 - f1-score (micro avg) 0.5223
135
+ 2023-10-20 09:23:24,095 saving best model
136
+ 2023-10-20 09:23:24,133 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-20 09:23:26,643 epoch 5 - iter 154/1546 - loss 0.12664182 - time (sec): 2.51 - samples/sec: 5226.08 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-20 09:23:29,036 epoch 5 - iter 308/1546 - loss 0.13916018 - time (sec): 4.90 - samples/sec: 5224.75 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-20 09:23:31,417 epoch 5 - iter 462/1546 - loss 0.14351088 - time (sec): 7.28 - samples/sec: 5221.91 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-20 09:23:33,823 epoch 5 - iter 616/1546 - loss 0.14577952 - time (sec): 9.69 - samples/sec: 5198.34 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-20 09:23:36,213 epoch 5 - iter 770/1546 - loss 0.14852475 - time (sec): 12.08 - samples/sec: 5162.44 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-20 09:23:38,571 epoch 5 - iter 924/1546 - loss 0.14575396 - time (sec): 14.44 - samples/sec: 5178.76 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-20 09:23:41,071 epoch 5 - iter 1078/1546 - loss 0.14710420 - time (sec): 16.94 - samples/sec: 5184.88 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-20 09:23:43,431 epoch 5 - iter 1232/1546 - loss 0.14875112 - time (sec): 19.30 - samples/sec: 5162.22 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-20 09:23:45,866 epoch 5 - iter 1386/1546 - loss 0.15024416 - time (sec): 21.73 - samples/sec: 5150.08 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-20 09:23:48,241 epoch 5 - iter 1540/1546 - loss 0.14764070 - time (sec): 24.11 - samples/sec: 5134.71 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-20 09:23:48,330 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-20 09:23:48,330 EPOCH 5 done: loss 0.1474 - lr: 0.000017
149
+ 2023-10-20 09:23:49,403 DEV : loss 0.0924314334988594 - f1-score (micro avg) 0.543
150
+ 2023-10-20 09:23:49,414 saving best model
151
+ 2023-10-20 09:23:49,448 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-20 09:23:51,812 epoch 6 - iter 154/1546 - loss 0.11599985 - time (sec): 2.36 - samples/sec: 5319.11 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-20 09:23:54,241 epoch 6 - iter 308/1546 - loss 0.12632791 - time (sec): 4.79 - samples/sec: 5163.22 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-20 09:23:56,387 epoch 6 - iter 462/1546 - loss 0.13301169 - time (sec): 6.94 - samples/sec: 5434.71 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-20 09:23:58,510 epoch 6 - iter 616/1546 - loss 0.13389940 - time (sec): 9.06 - samples/sec: 5547.70 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-20 09:24:00,637 epoch 6 - iter 770/1546 - loss 0.13455641 - time (sec): 11.19 - samples/sec: 5572.60 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-20 09:24:02,964 epoch 6 - iter 924/1546 - loss 0.13548871 - time (sec): 13.52 - samples/sec: 5506.63 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-20 09:24:05,387 epoch 6 - iter 1078/1546 - loss 0.13801768 - time (sec): 15.94 - samples/sec: 5515.90 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-20 09:24:07,751 epoch 6 - iter 1232/1546 - loss 0.13738306 - time (sec): 18.30 - samples/sec: 5434.50 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-20 09:24:10,100 epoch 6 - iter 1386/1546 - loss 0.13781890 - time (sec): 20.65 - samples/sec: 5409.32 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-20 09:24:12,462 epoch 6 - iter 1540/1546 - loss 0.13895651 - time (sec): 23.01 - samples/sec: 5385.41 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-20 09:24:12,553 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-20 09:24:12,553 EPOCH 6 done: loss 0.1391 - lr: 0.000013
164
+ 2023-10-20 09:24:13,648 DEV : loss 0.09394099563360214 - f1-score (micro avg) 0.5667
165
+ 2023-10-20 09:24:13,660 saving best model
166
+ 2023-10-20 09:24:13,698 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-20 09:24:16,052 epoch 7 - iter 154/1546 - loss 0.12165657 - time (sec): 2.35 - samples/sec: 4933.80 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-20 09:24:18,408 epoch 7 - iter 308/1546 - loss 0.12673301 - time (sec): 4.71 - samples/sec: 4986.08 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-20 09:24:20,752 epoch 7 - iter 462/1546 - loss 0.12724155 - time (sec): 7.05 - samples/sec: 5074.12 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-20 09:24:23,143 epoch 7 - iter 616/1546 - loss 0.13164398 - time (sec): 9.44 - samples/sec: 5141.76 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-20 09:24:25,490 epoch 7 - iter 770/1546 - loss 0.12961218 - time (sec): 11.79 - samples/sec: 5191.62 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-20 09:24:27,806 epoch 7 - iter 924/1546 - loss 0.12903599 - time (sec): 14.11 - samples/sec: 5172.23 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-20 09:24:30,111 epoch 7 - iter 1078/1546 - loss 0.13147164 - time (sec): 16.41 - samples/sec: 5204.56 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-20 09:24:32,430 epoch 7 - iter 1232/1546 - loss 0.13360333 - time (sec): 18.73 - samples/sec: 5237.46 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-20 09:24:34,865 epoch 7 - iter 1386/1546 - loss 0.13374572 - time (sec): 21.17 - samples/sec: 5228.21 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-20 09:24:37,242 epoch 7 - iter 1540/1546 - loss 0.13407398 - time (sec): 23.54 - samples/sec: 5262.00 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-20 09:24:37,328 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-20 09:24:37,329 EPOCH 7 done: loss 0.1339 - lr: 0.000010
179
+ 2023-10-20 09:24:38,393 DEV : loss 0.0905207097530365 - f1-score (micro avg) 0.5603
180
+ 2023-10-20 09:24:38,405 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-20 09:24:40,567 epoch 8 - iter 154/1546 - loss 0.13063320 - time (sec): 2.16 - samples/sec: 5847.04 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-20 09:24:42,906 epoch 8 - iter 308/1546 - loss 0.14726772 - time (sec): 4.50 - samples/sec: 5529.76 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-20 09:24:45,318 epoch 8 - iter 462/1546 - loss 0.14619992 - time (sec): 6.91 - samples/sec: 5476.37 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-20 09:24:47,668 epoch 8 - iter 616/1546 - loss 0.14164336 - time (sec): 9.26 - samples/sec: 5352.41 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-20 09:24:50,048 epoch 8 - iter 770/1546 - loss 0.13670213 - time (sec): 11.64 - samples/sec: 5370.75 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-20 09:24:52,428 epoch 8 - iter 924/1546 - loss 0.13211631 - time (sec): 14.02 - samples/sec: 5397.13 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-20 09:24:54,766 epoch 8 - iter 1078/1546 - loss 0.12689569 - time (sec): 16.36 - samples/sec: 5364.07 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-20 09:24:57,169 epoch 8 - iter 1232/1546 - loss 0.12935143 - time (sec): 18.76 - samples/sec: 5300.15 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-20 09:24:59,555 epoch 8 - iter 1386/1546 - loss 0.12672051 - time (sec): 21.15 - samples/sec: 5295.12 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-20 09:25:01,921 epoch 8 - iter 1540/1546 - loss 0.12817406 - time (sec): 23.52 - samples/sec: 5259.15 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-20 09:25:02,014 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-20 09:25:02,014 EPOCH 8 done: loss 0.1286 - lr: 0.000007
193
+ 2023-10-20 09:25:03,129 DEV : loss 0.09427973628044128 - f1-score (micro avg) 0.5679
194
+ 2023-10-20 09:25:03,142 saving best model
195
+ 2023-10-20 09:25:03,183 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-20 09:25:05,584 epoch 9 - iter 154/1546 - loss 0.14790471 - time (sec): 2.40 - samples/sec: 5017.34 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-20 09:25:07,975 epoch 9 - iter 308/1546 - loss 0.13523772 - time (sec): 4.79 - samples/sec: 5137.52 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-20 09:25:10,387 epoch 9 - iter 462/1546 - loss 0.12483047 - time (sec): 7.20 - samples/sec: 5245.29 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-20 09:25:12,786 epoch 9 - iter 616/1546 - loss 0.12594618 - time (sec): 9.60 - samples/sec: 5261.51 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-20 09:25:15,158 epoch 9 - iter 770/1546 - loss 0.12504595 - time (sec): 11.97 - samples/sec: 5265.70 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-20 09:25:17,637 epoch 9 - iter 924/1546 - loss 0.12727744 - time (sec): 14.45 - samples/sec: 5207.78 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-20 09:25:19,958 epoch 9 - iter 1078/1546 - loss 0.12477542 - time (sec): 16.77 - samples/sec: 5179.25 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-20 09:25:22,309 epoch 9 - iter 1232/1546 - loss 0.12399062 - time (sec): 19.13 - samples/sec: 5194.17 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-20 09:25:24,716 epoch 9 - iter 1386/1546 - loss 0.12526472 - time (sec): 21.53 - samples/sec: 5190.83 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-20 09:25:27,063 epoch 9 - iter 1540/1546 - loss 0.12731966 - time (sec): 23.88 - samples/sec: 5184.05 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-20 09:25:27,157 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-20 09:25:27,157 EPOCH 9 done: loss 0.1271 - lr: 0.000003
208
+ 2023-10-20 09:25:28,255 DEV : loss 0.0943358764052391 - f1-score (micro avg) 0.5782
209
+ 2023-10-20 09:25:28,267 saving best model
210
+ 2023-10-20 09:25:28,306 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-20 09:25:30,676 epoch 10 - iter 154/1546 - loss 0.14121008 - time (sec): 2.37 - samples/sec: 5065.46 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-20 09:25:33,055 epoch 10 - iter 308/1546 - loss 0.12929657 - time (sec): 4.75 - samples/sec: 5177.61 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-20 09:25:35,475 epoch 10 - iter 462/1546 - loss 0.12661390 - time (sec): 7.17 - samples/sec: 5166.63 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-20 09:25:37,890 epoch 10 - iter 616/1546 - loss 0.12903656 - time (sec): 9.58 - samples/sec: 5216.30 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-20 09:25:40,295 epoch 10 - iter 770/1546 - loss 0.12930312 - time (sec): 11.99 - samples/sec: 5208.12 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-20 09:25:42,742 epoch 10 - iter 924/1546 - loss 0.12539197 - time (sec): 14.44 - samples/sec: 5263.47 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-20 09:25:44,959 epoch 10 - iter 1078/1546 - loss 0.12288240 - time (sec): 16.65 - samples/sec: 5331.84 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-20 09:25:47,142 epoch 10 - iter 1232/1546 - loss 0.12366919 - time (sec): 18.84 - samples/sec: 5327.15 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-20 09:25:49,497 epoch 10 - iter 1386/1546 - loss 0.12424106 - time (sec): 21.19 - samples/sec: 5294.21 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-20 09:25:51,836 epoch 10 - iter 1540/1546 - loss 0.12454482 - time (sec): 23.53 - samples/sec: 5268.60 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-20 09:25:51,918 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-20 09:25:51,918 EPOCH 10 done: loss 0.1244 - lr: 0.000000
223
+ 2023-10-20 09:25:53,010 DEV : loss 0.09444588422775269 - f1-score (micro avg) 0.5751
224
+ 2023-10-20 09:25:53,052 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-20 09:25:53,052 Loading model from best epoch ...
226
+ 2023-10-20 09:25:53,136 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
227
+ 2023-10-20 09:25:56,005
228
+ Results:
229
+ - F-score (micro) 0.5346
230
+ - F-score (macro) 0.2224
231
+ - Accuracy 0.3719
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.6030 0.6004 0.6017 946
237
+ BUILDING 0.3333 0.0162 0.0309 185
238
+ STREET 0.5000 0.0179 0.0345 56
239
+
240
+ micro avg 0.6002 0.4819 0.5346 1187
241
+ macro avg 0.4788 0.2115 0.2224 1187
242
+ weighted avg 0.5561 0.4819 0.4860 1187
243
+
244
+ 2023-10-20 09:25:56,005 ----------------------------------------------------------------------------------------------------